PDB MCP Server

A comprehensive Model Context Protocol server for accessing Protein Data Bank (PDB) with 28 structural biology tools for protein structure analysis

Local serverstdio

What is the PDB MCP server?

A comprehensive Model Context Protocol server for accessing Protein Data Bank (PDB) with 28 structural biology tools for protein structure analysis, validation, and comparison. That is what the pdb mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

A Model Context Protocol (MCP) server that provides access to the Protein Data Bank (PDB) - the worldwide repository of information about the 3D structures of proteins, nucleic acids, and complex assemblies.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • search_structures — Search PDB database for protein structures by keyword, protein name, or PDB ID
  • get_structure_info — Get detailed information for a specific PDB structure
  • download_structure — Download structure coordinates in various formats (PDB, mmCIF, mmTF, XML)
  • search_by_uniprot — Find PDB structures associated with a UniProt accession
  • get_structure_quality — Get structure quality metrics and validation data
  • Tools — The Tools tool exposed by this server
  • Resources — The Resources tool exposed by this server

Getting it running

The server ships on npm as npm, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. PDB's toolset — search_structures, get_structure_info, download_structure and 4 more — is a fair guide to whether it matches your workflow. It is maintained by Augmented-Nature; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against PDB's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_structuresSearch PDB database for protein structures by keyword, protein name, or PDB ID
get_structure_infoGet detailed information for a specific PDB structure
download_structureDownload structure coordinates in various formats (PDB, mmCIF, mmTF, XML)
search_by_uniprotFind PDB structures associated with a UniProt accession
get_structure_qualityGet structure quality metrics and validation data
ToolsThe Tools tool exposed by this server.
ResourcesThe Resources tool exposed by this server.

How to install the PDB MCP server

{
  "mcpServers": {
    "pdb": {
      "command": "npx",
      "args": ["-y", "npm"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use PDB to search structures.
  • Use PDB to get structure info.
  • Use PDB to download structure.

Frequently asked questions

It connects PDB to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (search_structures, get_structure_info, download_structure, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with PDB directly.